activity
20242026
collaborators

8 papers

cs.CV2026

Latent Denoising Improves Visual Alignment in Large Multimodal Models

Dhruv Parikh, Jacob Fein-Ashley, Rajgopal Kannan +1

Large Multimodal Models (LMMs) such as LLaVA are typically trained with an autoregressive language modeling objective, providing only indirect supervision to visual tokens. This of…

cs.LG2025

Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say

Jacob Fein-Ashley, Dhruv Parikh, Rajgopal Kannan +1

Open-source Large Language Models (LLMs) increasingly specialize by domain (e.g., math, code, general reasoning), motivating systems that leverage complementary strengths across mo…

cs.LG2025

SPECTRE: An FFT-Based Efficient Drop-In Replacement to Self-Attention for Long Contexts

Jacob Fein-Ashley, Neelesh Gupta, Rajgopal Kannan +1

Long-context transformers face significant efficiency challenges due to the quadratic cost of self-attention. However, many modern applications-from multi-turn dialogue to high-res…

cs.LG2025

Contextual Feedback Loops: Amplifying Deep Reasoning with Iterative Top-Down Feedback

Jacob Fein-Ashley, Rajgopal Kannan, Viktor Prasanna

Conventional deep networks rely on one-way backpropagation that overlooks reconciling high-level predictions with lower-level representations. We propose \emph{Contextual Feedback…

cs.CV2025

ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioning

Dhruv Parikh, Jacob Fein-Ashley, Tian Ye +2

Convolutional Neural Networks (CNN) and Vision Transformers (ViT) have dominated the field of Computer Vision (CV). Graph Neural Networks (GNN) have performed remarkably well acros…

cs.LG2025

Linear Diffusion Networks

Jacob Fein-Ashley

We present Linear Diffusion Networks (LDNs), a novel architecture that reinterprets sequential data processing as a unified diffusion process. Our model integrates adaptive diffusi…